Cargando…
Context-Fused Guidance for Image Captioning Using Sequence-Level Training
Recent image captioning models based on the encoder-decoder framework have achieved remarkable success in humanlike sentence generation. However, an explicit separation between encoder and decoder brings out a disconnection between the image and sentence. It usually leads to a rough image descriptio...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Hindawi
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8754620/ https://www.ncbi.nlm.nih.gov/pubmed/35035470 http://dx.doi.org/10.1155/2022/9743123 |